]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/asiancrush.py
[ard] Improve _VALID_URL (closes #25134) (#25198)
[youtube-dl.git] / youtube_dl / extractor / asiancrush.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from .kaltura import KalturaIE
8 from ..utils import extract_attributes
9
10
11 class AsianCrushIE(InfoExtractor):
12     _VALID_URL_BASE = r'https?://(?:www\.)?(?P<host>(?:(?:asiancrush|yuyutv|midnightpulp)\.com|cocoro\.tv))'
13     _VALID_URL = r'%s/video/(?:[^/]+/)?0+(?P<id>\d+)v\b' % _VALID_URL_BASE
14     _TESTS = [{
15         'url': 'https://www.asiancrush.com/video/012869v/women-who-flirt/',
16         'md5': 'c3b740e48d0ba002a42c0b72857beae6',
17         'info_dict': {
18             'id': '1_y4tmjm5r',
19             'ext': 'mp4',
20             'title': 'Women Who Flirt',
21             'description': 'md5:7e986615808bcfb11756eb503a751487',
22             'timestamp': 1496936429,
23             'upload_date': '20170608',
24             'uploader_id': 'craig@crifkin.com',
25         },
26     }, {
27         'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
28         'only_matching': True,
29     }, {
30         'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/',
31         'only_matching': True,
32     }, {
33         'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/',
34         'only_matching': True,
35     }, {
36         'url': 'https://www.midnightpulp.com/video/010400v/drifters/',
37         'only_matching': True,
38     }, {
39         'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/',
40         'only_matching': True,
41     }, {
42         'url': 'https://www.cocoro.tv/video/the-wonderful-wizard-of-oz/008878v-the-wonderful-wizard-of-oz-ep01/',
43         'only_matching': True,
44     }]
45
46     def _real_extract(self, url):
47         mobj = re.match(self._VALID_URL, url)
48         host = mobj.group('host')
49         video_id = mobj.group('id')
50
51         webpage = self._download_webpage(url, video_id)
52
53         entry_id, partner_id, title = [None] * 3
54
55         vars = self._parse_json(
56             self._search_regex(
57                 r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
58                 default='{}'), video_id, fatal=False)
59         if vars:
60             entry_id = vars.get('entry_id')
61             partner_id = vars.get('partner_id')
62             title = vars.get('vid_label')
63
64         if not entry_id:
65             entry_id = self._search_regex(
66                 r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id')
67
68         player = self._download_webpage(
69             'https://api.%s/embeddedVideoPlayer' % host, video_id,
70             query={'id': entry_id})
71
72         kaltura_id = self._search_regex(
73             r'entry_id["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', player,
74             'kaltura id', group='id')
75
76         if not partner_id:
77             partner_id = self._search_regex(
78                 r'/p(?:artner_id)?/(\d+)', player, 'partner id',
79                 default='513551')
80
81         description = self._html_search_regex(
82             r'(?s)<div[^>]+\bclass=["\']description["\'][^>]*>(.+?)</div>',
83             webpage, 'description', fatal=False)
84
85         return {
86             '_type': 'url_transparent',
87             'url': 'kaltura:%s:%s' % (partner_id, kaltura_id),
88             'ie_key': KalturaIE.ie_key(),
89             'id': video_id,
90             'title': title,
91             'description': description,
92         }
93
94
95 class AsianCrushPlaylistIE(InfoExtractor):
96     _VALID_URL = r'%s/series/0+(?P<id>\d+)s\b' % AsianCrushIE._VALID_URL_BASE
97     _TESTS = [{
98         'url': 'https://www.asiancrush.com/series/012481s/scholar-walks-night/',
99         'info_dict': {
100             'id': '12481',
101             'title': 'Scholar Who Walks the Night',
102             'description': 'md5:7addd7c5132a09fd4741152d96cce886',
103         },
104         'playlist_count': 20,
105     }, {
106         'url': 'https://www.yuyutv.com/series/013920s/peep-show/',
107         'only_matching': True,
108     }, {
109         'url': 'https://www.midnightpulp.com/series/016375s/mononoke/',
110         'only_matching': True,
111     }, {
112         'url': 'https://www.cocoro.tv/series/008549s/the-wonderful-wizard-of-oz/',
113         'only_matching': True,
114     }]
115
116     def _real_extract(self, url):
117         playlist_id = self._match_id(url)
118
119         webpage = self._download_webpage(url, playlist_id)
120
121         entries = []
122
123         for mobj in re.finditer(
124                 r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL,
125                 webpage):
126             attrs = extract_attributes(mobj.group(0))
127             if attrs.get('class') == 'clearfix':
128                 entries.append(self.url_result(
129                     mobj.group('url'), ie=AsianCrushIE.ie_key()))
130
131         title = self._html_search_regex(
132             r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
133             'title', default=None) or self._og_search_title(
134             webpage, default=None) or self._html_search_meta(
135             'twitter:title', webpage, 'title',
136             default=None) or self._search_regex(
137             r'<title>([^<]+)</title>', webpage, 'title', fatal=False)
138         if title:
139             title = re.sub(r'\s*\|\s*.+?$', '', title)
140
141         description = self._og_search_description(
142             webpage, default=None) or self._html_search_meta(
143             'twitter:description', webpage, 'description', fatal=False)
144
145         return self.playlist_result(entries, playlist_id, title, description)